Apollo shoots for the stars with AI weapon for Coronavirus fight
A bleeding edge machine learning platform fashioned through artificial Intelligence is being hailed as a critical new weapon in the fight against coronavirus.
Apollo, developed by Cambridge UK business Agxio, rocketed off the launchpad today.
The Apollo technology operates beyond-human-scale performance, enabling the robotic platform to evaluate critical data to produce predictive models to solve real world problems. It then optimises these to look for patterns or configurations of parameters that human modellers may not even consider or have the patience to develop – all in a matter of hours.
Cambridge Science Park-based Agxio, which also has premises on the Aberystwyth Innovation & Enterprise Campus and is backed by the Welsh Government, is offering free use of the platform, together with its technical support team, to all credible researchers, practitioners and government bodies working to defeat COVID-19 for the duration of the pandemic.
Agxio has specially created a single COVID-19 data portal for the global community. Coviddata.io is open to any parties for augmentation as cases, data and innovations evolve.
Agxio is keen to hear from any data scientists and Python machine learning programmers who would like to volunteer support to researchers’ projects. To put your COVID-19 initiative forward for access to the Apollo platform, or volunteer your technical expertise to projects, contact Covid-19 [at] agxio.com
With the appropriate data, Apollo and the power of machine learning can be used to analyse and predict the efficacy of potential vaccine combinations, outbreak trends, behavioural nudge factors, early warning indicators, medical images against risk indicators and isolation rate projections.
These are just some of the potential applications envisaged by Agxio; it says the full range of use cases for automated machine learning is limitless.
Vitally, the fully automated AI-driven engine doesn’t require the user to be a programming expert or data scientist specialist – enabling an expert in a non-data science or machine learning field to be able to study ideas or data that would otherwise take years of experience to be able to apply.
Agxio CEO and co-founder, Dr Stephen Christie says: “What’s different about Apollo is that this is AI built by AI. It’s the machine building the machines, a series of robots building the best brains to answer targeted questions.
“Apollo is designed to focus on problems that are beyond human scale in dimension or complexity and is, without doubt, the most advanced approach of its kind.
“What would take a human literally weeks and months to do, Apollo can generate in minutes and hours. Machine learning is one of the most important tools and defining technologies of our generation, and Apollo is a complete game-changer in terms of accelerating the building of machine learning and solutions.
“While humans naturally tend to have biases, Apollo doesn’t have any and is additionally data-agnostic. Most importantly, Apollo is said to have speed and accuracy – and, right now, we need both to be really responsive to the situation.
“Accurate evaluation of data is vital in the Government’s planning of next-step measures. I think it is critical for the Government to be using the best tools and techniques we have available at this time.
“If you are going to do anything around research and machine learning, data is critical – as is the sharing and pooling of that data in a properly trusted and curated form, and making the data accessible and available to researchers.
“When making projections on isolation rates and strategies, you need real data and an engine that is able to crunch that data in a structured way, which is Apollo.
“You also need the data to be carefully curated and comprehensive. If you don’t have either of those you’re going to struggle to come up with the correct answer.”
Apollo was originally developed as an expert system to enable arable farmers to analyse traditional and advanced IoT data to address the growing population’s needs for improved yields and disease resistance.
It has since proved to be a powerful tool for a number of different applications including fraud analytics, disease detection, economic anomalies, and bio-sequencing applications – automating the role of the data scientist to build optimal machine learning models against a target prediction. Data-agnostic, it can operate on numerical, textual and image data, both on and off premises.
• To read the latest edition of Business Weekly visit https://bit.ly/2xMd8Di